Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2981 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1287777 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0950. Min Act: -0.0000

Data Index: 72661 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1100856 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0893. Min Act: -0.0000

Data Index: 81942 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0893. Min Act: -0.0000

Data Index: 258282 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0841. Min Act: -0.0000

Data Index: 783087 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1736456 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1062801 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0802. Min Act: -0.0000

Data Index: 891441 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0782. Min Act: -0.0000

Data Index: 265054 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0774. Min Act: -0.0000

Data Index: 226379 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1678326 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0718. Min Act: -0.0000

Data Index: 521715 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0715. Min Act: -0.0000

Data Index: 99942 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0713. Min Act: -0.0000

Data Index: 891839 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0704. Min Act: -0.0000

Data Index: 373530 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0702. Min Act: -0.0000

Data Index: 488101 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1050331 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0692. Min Act: -0.0000

Data Index: 389161 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1337978 (The Pile)

Max Activating Token Index: 1023